data poisoning

One attacks the model's inputs, the other its upbringing. The phase decides the defence, and interviewers want you to say so.

Detection alone loses: clean-label poisons look correct. The answer that scores builds a pipeline where poison is hard to add, easy to trace and contained when it slips through.

Every poisoned example looks correctly labelled to a reviewer. The scored answer explains the mechanism, why label audits miss it, and the defences that work at the pipeline level.

The intuition that a huge dataset dilutes poison turns out to be wrong for some attacks. The scored answer cites the evidence, explains why, and moves the defence to data provenance and testing.

'Clean the dataset' is not an investigation. The answer freezes evidence, traces what changed and who could change it, tests causality by retraining, and treats the pipeline as possibly compromised too.